EADReg: Probabilistic Correspondence Generation with Efficient Autoregressive Diffusion Model for Outdoor Point Cloud Registration

TL;DR

EADReg introduces an autoregressive diffusion model for outdoor LiDAR point cloud registration, combining coarse outlier rejection with fine correspondence refinement, achieving state-of-the-art accuracy with efficient runtime.

Contribution

The paper presents a novel autoregressive diffusion framework for outdoor LiDAR point cloud registration, addressing sparsity and irregularity challenges with a coarse-to-fine approach.

Findings

Achieves state-of-the-art registration accuracy on KITTI and NuScenes datasets.

Runs at comparable speed to convolutional-based methods.

Effectively handles outdoor LiDAR point cloud challenges.

Abstract

Diffusion models have shown the great potential in the point cloud registration (PCR) task, especially for enhancing the robustness to challenging cases. However, existing diffusion-based PCR methods primarily focus on instance-level scenarios and struggle with outdoor LiDAR points, where the sparsity, irregularity, and huge point scale inherent in LiDAR points pose challenges to establishing dense global point-to-point correspondences. To address this issue, we propose a novel framework named EADReg for efficient and robust registration of LiDAR point clouds based on autoregressive diffusion models. EADReg follows a coarse-to-fine registration paradigm. In the coarse stage, we employ a Bi-directional Gaussian Mixture Model (BGMM) to reject outlier points and obtain purified point cloud pairs. BGMM establishes correspondences between the Gaussian Mixture Models (GMMs) from the source and target frames, enabling reliable coarse registration based on filtered features and geometric information. In the fine stage, we treat diffusion-based PCR as an autoregressive process to generate robust point correspondences, which are then iteratively refined on upper layers. Despite common criticisms of diffusion-based methods regarding inference speed, EADReg achieves runtime comparable to convolutional-based methods. Extensive experiments on the KITTI and NuScenes benchmark datasets highlight the state-of-the-art performance of our proposed method. Codes will be released upon publication.